检索结果-内蒙古大学图书馆

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Pirnau Mironela Priescu Iustin Priescu Catalina Mihaela Pirnau Claudiu Ghiculescu Liviu Daniel Department of Informatics Faculty of Informatics “Titu Maiorescu” University Bucharest Romania Faculty of Automatic Control and Computer Science National University of Science and Technology POLITEHNICA Bucharest Bucharest Romania Manufacturing Engineering Department Faculty of Industrial Engineering and Robotics National University of Science and Technology POLITEHNICA Bucharest Bucharest Romania

ISBN: (数字)9798350371154

ISBN: (纸本)9798350371161

This study proposes methods that can be used to examine and interpret comments that users have made after watching videos on YouTube on a particular topic. YouTube tutorials are very popular among young people. They have become an important pillar in informal education, thus contributing to the rapid acquisition of skills and knowledge. Under these circumstances, we were interested in analysing the YouTube videos comments, knowing that the platform has a continuous increase in popularity, which is also due to the opportunities of sharing them. Since ChatGPT-themed YouTube videos have seen a significant surge in popularity since 2022, we were interested to analyse some videos that approach the topics of “ChatGPT, AI clone, AI robot and Deep Learning.”

关键词： Video on demand Social networking (online) Education Tutorials Chatbots Web sites Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning

arXiv

引用

arXiv 2024年

作者： Hao, Zhiwei Guo, Jianyuan Shen, Li Luo, Yong Hu, Han Wen, Yonggang School of Information and Electronics Beijing Institute of Technology Beijing China School of Computer Science Faculty of Engineering The University of Sydney Sydney Australia School of Cyber Science and Technology Sun Yat-sen University Shenzhen China School of Computer Science Wuhan University Wuhan China School of Computer Science and Engineering Nanyang Technological University Singapore

Recent advancements in multimodal fusion have witnessed the remarkable success of vision-language (VL) models, which excel in various multimodal applications such as image captioning and visual question answering. However, building VL models requires substantial hardware resources, where efficiency is restricted by two key factors: the extended input sequence of the language model with vision features demands more computational operations, and a large number of additional learnable parameters increase memory complexity. These challenges significantly restrict the broader applicability of such models. To bridge this gap, we propose ADEM-VL, an efficient vision-language method that tunes VL models based on pretrained large language models (LLMs) by adopting a parameter-free cross-attention mechanism for similarity measurements in multimodal fusion. This approach only requires embedding vision features into the language space, significantly reducing the number of trainable parameters and accelerating both training and inference speeds. To enhance representation learning in fusion module, we introduce an efficient multiscale feature generation scheme that requires only a single forward pass through the vision encoder. Moreover, we propose an adaptive fusion scheme that dynamically discards less relevant visual information for each text token based on its attention score. This ensures that the fusion process prioritizes the most pertinent visual features. With experiments on various tasks including visual question answering, image captioning, and instruction-following, we demonstrate that our framework outperforms existing approaches. Specifically, our method surpasses existing methods by an average accuracy of 0.77% on scienceQA dataset, with reduced training and inference latency, demonstrating the superiority of our framework. The code is available at https://***/Hao840/ADEM-VL. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Luenberger observer for velocity estimation in active magnetic levitation system

Nonlinear Luenberger observer for velocity estimation in act...

引用

International Conference on Methods and Models in Automation and Robotics (MMAR)

作者： Rafał Bieszczad Adam Piłat Department of Automatic Control and Robotics Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering AGH University of Science and Technology Cracow Poland

This article presents the problem of designing a nonlinear observer for an active magnetic suspension system. The design process of the nonlinear Luenberger observer (also known as the Kazantzis-Kravaris-Luenberger observer) is discussed. Particular attention was paid to the main nonlinearity of the system - the electromagnetic force, which was modeled applying the function describing the change in inductance as a function of the distance of the levitating object from the electromagnet surface. Theoretical analyses were confirmed by the results of experimental studies in which the task of moving the sphere between the given positions using current control was carried out. control tasks were conducted in the real-time regime on an embedded platform. The measured signals and estimated velocity were analyzed in the context of future implementations in control applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The strong substructure and feature attention mechanism for image semantic segmentation

The strong substructure and feature attention mechanism for ...

引用

作者： Zhang, Yuhang Ren, Hongshuai Yang, Wensi Wang, Yang Ye, Kejiang Xu, Cheng-Zhong Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China Alibaba Cloud Alibaba Group Hangzhou China State Key Laboratory of IoT for Smart City University of Macau China

Semantic segmentation is a hot topic in computer vision and various deep learning networks are designed to achieve higher accuracy on that by fully exploring the capability of neural networks. This paper aims to address the issue and proposes the substructures with novelty for popular networks. Meanwhile, we present a cross-channel structure, which simultaneously reduces parameter while the kernel size becomes larger. After that, to overcome the weakness of insufficient dataset which refers to satellite image data, we propose a feature attention mechanism with generative adversarial network to enhance the images' features. We show the recognition result on the satellite image dataset with a large picture. This paper evaluates substructures on the PASCAL VOC2012 dataset and improves the mIOU from 74.68% to 88.15%. © 2020 John Wiley & Sons, Ltd.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Intelligent Optimization of Laser Marking Parameters Using Neural Networks and Genetic Algorithms

Intelligent Optimization of Laser Marking Parameters Using N...

引用

Robotics, Automation and Artificial Intelligence (RAAI), IEEE International Conference on

作者： Teng Yan Wenxian Li Zhenxi Yu Yuxiang Sun Haoxue Zhuang Xiaohong Zhou College of Applied Technology Shenzhen University Shenzhen China Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen China College of Big Data and Internet Shenzhen Technology University Shenzhen China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Faculty of Computer Science and Business Information Systems Technical University of Applied Sciences Würzburg-Schweinfurt Wtirzburg -Schweinfurt Germany

ISBN: (数字)9798331520038

ISBN: (纸本)9798331520045

Laser marking technology is essential in precision manufacturing, but optimizing its numerous parameters is com-plex and time-consuming with traditional methods. This study developed a fully automated laser marking system using the Draco series laser from Han's Laser, incorporating automatic loading and unloading mechanisms. By utilizing neural networks and genetic algorithms, we optimized laser marking on ABS materials. The research included COMSOL simulations of laser-material interactions, analysis of parameter variations on col-oration, temperature field distribution under laser irradiation, and prediction of marking effects for practical applications. The aim is to automate processes through algorithmic integration, providing an intelligent laser marking solution. The developed methodologies and algorithms are applicable to other manufac-turing optimizations, offering valuable insights for broader in-dustrial applications. Primary research focuses include COMSOL simulation and parameter analysis, developing an AI-integrated laser production line with color prediction, and exploring au-tomated laser marking on ABS material using neural networks and genetic algorithms.

关键词： Analytical models Temperature distribution Radiation effects Lasers Neural networks Predictive models Prediction algorithms Optimization Robots Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Low-profile Broadband Dual-polarized Magneto-electric Dipole Antenna for 5G Applications

A Low-profile Broadband Dual-polarized Magneto-electric Dipo...

引用

World Congress on Computing and Communication Technologies (WCCCT)

作者： Yihuang Yang Botao Feng Xiao Ding Li Deng Wenzhe Gu Kwok L. Chung College of Electronics and Information Engineering Shenzhen University Shenzhen China Faculty of Humanities and Arts Macau University of Science and Technology Macau China College of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China School of Computer Science and Engineering Huizhou University Huizhou China School of Intelligent Manufacturing and Electrical Engineering Guangzhou Institute of Science and Technology Guangdong China

ISBN: (数字)9798331512620

ISBN: (纸本)9798331512637

This study proposes a compact wideband dual-polarized (DP) magneto-electric (ME) dipole antenna with cross-differential feeding, designed for 5G/6G millimeter-wave (mm-Wave) systems. The antenna features a geometrically symmetric configuration, integrating radiating elements and feeding networks into a single metallic layer, achieving a low-profile structure. By leveraging ME coupling mechanisms, the antenna supports dual-orthogonal polarization operation, offering a broad impedance bandwidth of 39.4% (26.3-39.1 GHz) under differential port excitation. Experimental results demonstrate excellent radiation performance, including highly symmetric radiation patterns, cross-polarization suppression below -30 dB, a gain range of 2.6-6.2 dBi, and an axial ratio (AR) below 2 dB across the operational band. The unified feed-radiator co-design effectively mitigates mm-Wave challenges such as narrow bandwidth and integration constraints commonly found in conventional dual-polarized antennas, which makes the proposed design a promising solution for compact MIMO arrays in the 28/39 GHz 5G NR bands.

关键词： Wireless communication Dipole antennas Magnetoelectric effects Microstrip antennas Directive antennas Antenna feeds Broadband communication Broadband antennas Wideband Gain

来源：评论

学校读者我要写书评

暂无评论

Genome engineering of the human gut microbiome

引用

Journal of Genetics and Genomics 2024年第5期51卷 479-491页

作者： Linggang Zheng Juntao Shen Ruiyue Chen Yucan Hu Wei Zhao Elaine Lai-Han Leung Lei Dai Dr Neher's Biophysics Laboratory for Innovative Drug Discovery/State Key Laboratory of Quality Research in Chinese Medicine Macao University of Science and TechnologyTaipaMacao 999078China CAS Key Laboratory of Quantitative Engineering Biology Shenzhen Institute of Synthetic BiologyShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China University of Chinese Academy of Sciences Beijing 100049China Cancer Center Faculty of Health ScienceUniversity of MacaoMacao 999078China MOE Frontiers Science Center for Precision Oncology University of MacaoMacao 999078China

The human gut microbiome,a complex ecosystem,significantly influences host health,impacting crucial aspects such as metabolism and *** enhance our comprehension and control of the molecular mechanisms orchestrating the intricate interplay between gut commensal bacteria and human health,the exploration of genome engineering for gut microbes is a promising ***,the complexities and diversities inherent in the gut microbiome pose substantial challenges to the development of effective genome engineering tools for human gut *** this comprehensive review,we provide an overview of the current progress and challenges in genome engineering of human gut commensal bacteria,whether executed in vitro or in situ.A specific focus is directed towards the advancements and prospects in cargo DNA delivery and high-throughput ***,we elucidate the immense potential of genome engineering methods to enhance our understanding of the human gut microbiome and engineer the microorganisms to enhance human health.

关键词： Non-model gut commensals Genomeediting reagents Cargo delivery High-throughput genome engineering

来源：评论

学校读者我要写书评

暂无评论

Explainable-AI-based two-stage solution for WSN object localization using zero-touch mobile transceivers

引用

science China(Information sciences) 2024年第7期67卷 27-45页

作者： Kai FANG Junxin CHEN Han ZHU Thippa Reddy GADEKALLU Xiaoping WU Wei WANG School of Mathematics and Computer Science Zhejiang A&F University School of Software Dalian University of Technology Faculty of Applied Sciences Macao Polytechnic University Department of Electrical and Computer Engineering Lebanese American University School of Information Engineering Huzhou University Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University

Artificial intelligence technology is widely used in the field of wireless sensor networks(WSN).Due to its inexplicability, the interference factors in the process of WSN object localization cannot be effectively eliminated. In this paper, an explainable-AI-based two-stage solution is proposed for WSN object localization. In this solution, mobile transceivers are used to enlarge the positioning range and eliminate the blind area for object localization. The motion parameters of transceivers are considered to be unavailable,and the localization problem is highly nonlinear with respect to the unknown parameters. To address this,an explainable AI model is proposed to solve the localization problem. Since the relationship among the variables is difficult to fully include in the first-stage traditional model, we develop a two-stage explainable AI solution for this localization problem. The two-stage solution is actually a comprehensive consideration of the relationship between variables. The solution can continue to use the constraints unused in the firststage during the second-stage, thereby improving the performance of the solution. Therefore, the two-stage solution has stronger robustness compared to the closed-form solution. Experimental results show that the performance of both the two-stage solution and the traditional solution will be affected by numerical changes in unknown parameters. However, the two-stage solution performs better than the traditional solution, especially with a small number of mobile transceivers and sensors or in the presence of high noise. Furthermore,we have also verified the feasibility of the proposed explainable-AI-based two-stage solution.

关键词： explainable AI object localization semidefinite relaxation mobile transceiver two-stage solution closed-form solution

来源：评论

学校读者我要写书评

暂无评论

A Dual Broadband Antenna for V2X, LTE, and 5G Vehicular Communication Systems

A Dual Broadband Antenna for V2X, LTE, and 5G Vehicular Comm...

引用

IEEE International Conference on Electronic Information and Communication technology (ICEICT)

作者： Yiting Hu Botao Feng Kwok L. Chung Xiao Ding Wenzhe Gu Li Deng College of Electronics and Information Engineering Shenzhen University Shenzhen China School of Computer Science and Engineering Huizhou University Huizhou China Faculty of Humanities and Arts Macau University of Science and Technology Macau China College of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350384437

ISBN: (纸本)9798350384444

In this paper, we present a novel dual broadband antenna tailored for vehicular applications. The antenna design incorporates circular and square patches, metal cylinders, and conductive vias. Our simulated results demonstrate an impressive impedance bandwidth spanning from 3.71 GHz to 3.85 GHz for |S 11 |<-10 and from 4.47 GHz to 5.91 GHz for |S 22 |<-10, effectively covering crucial V2X, LTE, and early 5G frequency bands. Moreover, the proposed antenna showcases peak gains ranging from 5.62 dBi to 9.75 dBi, delivering exceptional directionality and wide beamwidth. These characteristics are aimed at ensuring reliable and efficient communication for modern vehicular systems, supporting advanced applications such as autonomous driving and advanced driver assistance system (ADAS).

关键词： 5G mobile communication Metals Directive antennas Distance measurement Broadband communication Information and communication technology Broadband antennas

来源：评论

学校读者我要写书评

暂无评论

A Material Identification Approach Based on Wi-Fi Signal

引用

computers, Materials & Continua 2021年第12期69卷 3383-3397页

作者： Chao Li Fan Li Wei Du Lihua Yin Bin Wang Chonghua Wang Tianjie Luo Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510700China PCL Research Center of Cyberspace Security Peng Cheng LaboratoryShenzhen518052China Department of Computer Science and Computer Engineering University of ArkansasFayetteville72701USA College of Electrical Engineering Zhejiang UniversityHangzhou310058China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Material identification is a technology that can help to identify the type of target *** approaches depend on expensive instruments,complicated pre-treatments and professional *** is difficult to find a substantial yet effective material identification method to meet the daily use *** this paper,we introduce a Wi-Fi-signal based material identification approach by measuring the amplitude ratio and phase difference as the key features in the material classifier,which can significantly reduce the cost and guarantee a high level *** practical measurement of WiFi based material identification,these two features are commonly interrupted by the software/hardware noise of the channel state information(CSI).To eliminate the inherent noise of CSI,we design a denoising method based on the antenna array of the commercial off-the-shelf(COTS)Wi-Fi *** that,the amplitude ratios and phase differences can be more stably utilized to classify the *** implement our system and evaluate its ability to identify materials in indoor *** result shows that our system can identify 10 commonly seen liquids with an average accuracy of 98.8%.It can also identify similar liquids with an overall accuracy higher than 95%,such as various concentrations of salt water.

关键词： Internet of Things Wi-Fi signal channel state information material identification noise elimination

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：